© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 222632
    Prev
    Next
    INDEX
    Explanations

    arrival, significant, event, What

    np_acts-logits-general · gemini-2.5-flash-lite

    list punctuation and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frowning
    0.49
    ení
    0.46
    ;*/
    0.46
    ø
    0.46
    ù
    0.46
    ලා
    0.46
    uoso
    0.45
     packing
    0.45
     frown
    0.45
     responsible
    0.44
    POSITIVE LOGITS
    ନ୍ତ
    0.51
    Him
    0.50
    Türk
    0.50
    Ceylon
    0.50
    蝼
    0.50
    Warum
    0.49
    Secrets
    0.49
    Ꮃ
    0.49
    Imper
    0.49
    Aryan
    0.49
    Activations Density 0.000%

    No Known Activations